Metraipolis › archive › dc_cbe2b374da21

Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition — arXiv:2609.13024

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13024
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:44.679Z
SHA-256 of the archived text
ba99e03a09d6fc457f154d644e2614a91e3513197b25d7149159962afe54c3a0
Stable URL of this page
https://metraipolis.com/documento/dc_cbe2b374da21

How to cite

Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition — arXiv:2609.13024 — arXiv (en), https://arxiv.org/abs/2609.13024 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbe2b374da21 (Metraipolis archive dc_cbe2b374da21, sha256 ba99e03a09d6fc457f154d644e2614a91e3513197b25d7149159962afe54c3a0)
BibTeX
@misc{dccbe2b374da21,
  title = {Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition — arXiv:2609.13024},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13024},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbe2b374da21; sha256 ba99e03a09d6fc457f154d644e2614a91e3513197b25d7149159962afe54c3a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13024. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student model for enhancing the latter's performance. In this work, we reviewed the feature knowledge distillation for 3D-CNNs and observed that most feature distillation methods in video analysis are simple adaptations of those used in image analysis, often neglecting the differences of video features in the temporal dimension. To address this issue, we proposed Label-Guided Knowledge Distillation (LGKD) to guide the distillation of student model features using ground truth labels. Our method entails two components: sample-wise distillation and class-wise distillation, enabling the student model to learn feature representation of the teacher model at two levels. Sample-wise distillation utilizes label information and the teacher's probability distribution to guide the learning of features that significantly impact temporal accuracy while mitigating noise. Meanwhile, class-wise feature distillation employs a prototype network to further capture the relational knowledge among samples within the same category, enhancing the student's ability to learn higher-dimensional semantic information and improving model generalization. To demonstrate the effectiveness and superiority of our method, we conducted comprehensive experiments on two benchmark action recognition datasets, UCF101 and HMDB51, achieving competitive results.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13024 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.967Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).